© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3982
    Prev
    Next
    INDEX
    Explanations

    references to people involved in crimes and their connection to legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    court cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.70
    DockStyle
    -0.60
     AssemblyCulture
    -0.58
    richTextPanel
    -0.56
     onPostExecute
    -0.54
    WithIOException
    -0.52
     crimin
    -0.52
    awtextra
    -0.52
    RegressionTest
    -0.51
     criminal
    -0.51
    POSITIVE LOGITS
     ujednoznacz
    0.60
    worship
    0.57
    TagMode
    0.57
    stø
    0.57
    nologies
    0.57
    AsStream
    0.56
    ########.
    0.55
     ketat
    0.54
     mû
    0.54
    ondissement
    0.54
    Activations Density 3.154%

    No Known Activations